Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks used in academic writing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     FetchType
    -1.00
    tvguidetime
    -1.00
    fastjson
    -0.89
    ugeot
    -0.86
    arangay
    -0.85
     GenerationType
    -0.85
    NUMX
    -0.84
    extAlignment
    -0.84
    səhifə
    -0.81
    TimerTask
    -0.80
    POSITIVE LOGITS
    ↵↵
    1.38
    <eos>
    1.14
    .
    1.13
     The
    1.04
     This
    1.01
     However
    1.00
     It
    0.95
     Also
    0.94
    ).
    0.92
    }.
    0.88
    Act Density 3.661%

    No Known Activations